Robust foreground detection and shadow removing using local intensity ratio

Author

Jin-Hai Xiang ; Hong-Hong Liao ; Ning Wang ; Heng Fan ; Wei-Ping Sun ; Yu Sheng-Sheng

Author_Institution

Sch. of Comput. Sci. & Technol., Huazhong Univ. of Sci. & Technol., Wuhan, China

Volume

02

fYear

2013

fDate

14-17 July 2013

Firstpage

962

Lastpage

967

Abstract

Segmenting foreground objects from video sequences in real time is a fundamental step for video surveillance. In this paper, a local intensity ratio (LIR) model is proposed, which is robust to illumination change. And the distribution of the LIR is also discussed. Normalized local intensity ratio instead of pixel intensity is used in Gaussian Mixture Model (GMM) to segment the foreground without shadow. Afterwards, we use the ratio between foreground and image size, and contour orientation to fill foreground with holes. Experimental results show that the proposed method can get foreground objects in real-time, and eliminate more shadow compared to existing shadow detection methods.

Keywords

Gaussian processes; image segmentation; image sequences; mixture models; video surveillance; GMM; Gaussian mixture model; LIR model; contour orientation; foreground object segmentation; foreground-image size ratio; illumination change robustness; normalized local intensity ratio model; robust foreground detection; shadow detection methods; shadow removal; video sequences; video surveillance; Abstracts; Image segmentation; Robustness; Foreground detection; Gaussian mixture model (GMM); Local intensity ratio (LIR); Shadow removal;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2013 International Conference on

Conference_Location

Tianjin

Type

conf

DOI

10.1109/ICMLC.2013.6890421

Filename

6890421